Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 713 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.6639. Min Range: -4.6639

Max Act: 4.6639. Min Act: -0.1700

Data Index: 4917803 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.6639. Min Range: -4.6639

Max Act: 4.5764. Min Act: -0.1700

Data Index: 1382435 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 4.6639. Min Range: -4.6639

Max Act: 4.5265. Min Act: -0.1700

Data Index: 1824970 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 4.6639. Min Range: -4.6639

Max Act: 4.5000. Min Act: -0.1700

Data Index: 6651998 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.6639. Min Range: -4.6639

Max Act: 4.4448. Min Act: -0.1700

Data Index: 3653420 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.6639. Min Range: -4.6639

Max Act: 4.4499. Min Act: -0.1700

Data Index: 6033634 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 4.6639. Min Range: -4.6639

Max Act: 4.4527. Min Act: -0.1700

Data Index: 7089442 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 4.6639. Min Range: -4.6639

Max Act: 4.4330. Min Act: -0.1700

Data Index: 4695169 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 4.6639. Min Range: -4.6639

Max Act: 4.4257. Min Act: -0.1700

Data Index: 7733468 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 4.6639. Min Range: -4.6639

Max Act: 4.4019. Min Act: -0.1700

Data Index: 1000791 (Open Web Text)

Max Activating Token Index: 31

Text #10

Max Range: 4.6639. Min Range: -4.6639

Max Act: 4.3899. Min Act: -0.1700

Data Index: 97591 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 4.6639. Min Range: -4.6639

Max Act: 4.3808. Min Act: -0.1700

Data Index: 4069815 (Open Web Text)

Max Activating Token Index: 197

Text #12

Max Range: 4.6639. Min Range: -4.6639

Max Act: 4.3980. Min Act: -0.1700

Data Index: 4489083 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 4.6639. Min Range: -4.6639

Max Act: 4.3858. Min Act: -0.1700

Data Index: 4649336 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 4.6639. Min Range: -4.6639

Max Act: 4.3713. Min Act: -0.1700

Data Index: 4653692 (Open Web Text)

Max Activating Token Index: 11

Text #15

Max Range: 4.6639. Min Range: -4.6639

Max Act: 4.4039. Min Act: -0.1700

Data Index: 2840667 (Open Web Text)

Max Activating Token Index: 9

Text #16

Max Range: 4.6639. Min Range: -4.6639

Max Act: 4.3844. Min Act: -0.1700

Data Index: 1470272 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 4.6639. Min Range: -4.6639

Max Act: 4.3836. Min Act: -0.1700

Data Index: 2960796 (Open Web Text)

Max Activating Token Index: 275

Text #18

Max Range: 4.6639. Min Range: -4.6639

Max Act: 4.3753. Min Act: -0.1700

Data Index: 5394446 (Open Web Text)

Max Activating Token Index: 14

Text #19

Max Range: 4.6639. Min Range: -4.6639

Max Act: 4.4043. Min Act: -0.1700

Data Index: 1479632 (Open Web Text)

Max Activating Token Index: 12